Our paper Transcriptomics-Conditioned Virtual Tissue Synthesis via Diffusion Transformers has been accepted at the ICML 2026 Workshop on Structured Data for Health (SD4H).

The work, in collaboration with Kalin Nonchev, Viktor Koelzer, and Gunnar Rätsch, introduces a diffusion-transformer framework that conditions on transcriptomics to synthesize high-resolution virtual tissue, bridging spatial omics and computational pathology.